© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 2311
    Prev
    Next
    INDEX
    Explanations

    mentions of defensemen in the context of hockey

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to defensive players in sports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Lerner
    -0.73
     ABE
    -0.71
     Goodell
    -0.70
     Canaver
    -0.68
     Haram
    -0.64
     Yor
    -0.63
     Bundy
    -0.63
     Terra
    -0.62
     Faw
    -0.61
     Hou
    -0.60
    POSITIVE LOGITS
    men
    1.09
    man
    0.94
    ²¾
    0.87
    emate
    0.82
     pairing
    0.80
    pair
    0.79
    achev
    0.79
     misc
    0.78
    erman
    0.78
    units
    0.78
    Activations Density 0.085%

    No Known Activations